Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    execute a request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countless
    0.47
     facets
    0.46
     statunit
    0.44
     offices
    0.43
     aforementioned
    0.42
     d
    0.42
     m
    0.40
     dalla
    0.40
     groundbreaking
    0.40
     decades
    0.39
    POSITIVE LOGITS
    ądź
    0.54
    หรือ
    0.47
    анг
    0.46
     тоже
    0.46
     భాష
    0.44
    栞
    0.44
     또
    0.44
    ที่จะ
    0.44
     Продол
    0.44
    อย่าง
    0.43
    Act Density 0.004%

    No Known Activations